Update README.md
Browse files
README.md
CHANGED
|
@@ -11,24 +11,12 @@ pipeline_tag: image-classification
|
|
| 11 |
---
|
| 12 |
|
| 13 |
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
### Recommendations
|
| 17 |
-
|
| 18 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 19 |
-
|
| 20 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
[More Information Needed]
|
| 25 |
-
|
| 26 |
## Training Details
|
| 27 |
|
| 28 |
### Training Data
|
| 29 |
This model was trained on the Eurosat dataset containing Sentinel-2 satellite images available at ```blanchon/EuroSAT_RGB```
|
| 30 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 31 |
-
The Eurosat dataset consists of ten classes
|
| 32 |
- Annual Crop
|
| 33 |
- Forest
|
| 34 |
- Herbaceous Vegetation
|
|
@@ -68,18 +56,11 @@ The Eurosat dataset consists of ten classes
|
|
| 68 |
|
| 69 |
#### Testing Data
|
| 70 |
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
[More Information Needed]
|
| 74 |
-
|
| 75 |
-
#### Factors
|
| 76 |
-
|
| 77 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 78 |
-
|
| 79 |
-
[More Information Needed]
|
| 80 |
|
| 81 |
#### Metrics
|
| 82 |
Model Accuracy: 88%
|
|
|
|
| 83 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 84 |
|
| 85 |
[More Information Needed]
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
## Training Details
|
| 15 |
|
| 16 |
### Training Data
|
| 17 |
This model was trained on the Eurosat dataset containing Sentinel-2 satellite images available at ```blanchon/EuroSAT_RGB```
|
| 18 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 19 |
+
The Eurosat dataset consists of ten classes and the a total of 27,000 images with a training set size of 16,200 images
|
| 20 |
- Annual Crop
|
| 21 |
- Forest
|
| 22 |
- Herbaceous Vegetation
|
|
|
|
| 56 |
|
| 57 |
#### Testing Data
|
| 58 |
|
| 59 |
+
- 5400 images
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
#### Metrics
|
| 62 |
Model Accuracy: 88%
|
| 63 |
+
model Recall: 88%
|
| 64 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 65 |
|
| 66 |
[More Information Needed]
|